© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 186298
    Prev
    Next
    INDEX
    Explanations

    foreign languages and multiple meanings

    np_acts-logits-general · gemini-2.5-flash-lite

    year and month specific information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LN
    0.49
    जम
    0.49
    R
    0.49
    mills
    0.48
    rownames
    0.47
    P
    0.46
    +
    0.46
    Rat
    0.46
    Pod
    0.45
    *
    0.45
    POSITIVE LOGITS
     πολλά
    0.58
     hệ
    0.53
     Sección
    0.53
     toujours
    0.51
     can
    0.50
     τόσο
    0.49
     Andrés
    0.49
     আজ
    0.48
     is
    0.48
     fateful
    0.47
    Activations Density 0.000%

    No Known Activations